Motion Sensing Wearable Apparatus For Evaluating Action Quality

Abstract

Provided are methods and apparatuses for action quality evaluation using a wearable device having a motion sensor, where the method includes: obtaining motion data from the motion sensor collected during a fitness activity of a user associated with the wearable device; determining a value of at least one movement evaluation metric of the user based on the motion data; and determining an action quality evaluation result of the user based on the value of at least one movement evaluation metric.

What is claimed is: 
     
         1 . A method for evaluating action quality using a wearable device comprising a motion sensor, comprising:
 obtaining, by a processor, motion data from the motion sensor collected during a fitness activity of a user associated with the wearable device;   determining, by the processor, a value of at least one action evaluation metric of the user according to the motion data; and   determining, by the processor, an action quality evaluation result of the user according to the value of the at least one action evaluation metric;   wherein the at least one action evaluation metric comprises at least one of:   an action consistency metric, for evaluating a consistency of at least one of amplitudes or rhythms of multiple fitness actions performed by the user;   an action stability metric, for evaluating a degree of jitter or wobble of at least one of the multiple fitness actions performed by the user during the fitness activity;   an action continuity metric, for evaluating a continuity degree of at least one of the multiple fitness actions;   an action variability metric, for evaluating an intensity variability of the multiple fitness actions; or   a force control metric, for evaluating force exertion condition during at least one of the multiple fitness actions.   
     
     
         2 . The method according to  claim 1 , wherein determining the value of the at least one action evaluation metric of the user according to the motion data comprises:
 extracting, from the motion data by the processor, metric feature data corresponding to each of at least a part of the multiple fitness actions performed by the user; and   determining, by the processor, the value of the at least one action evaluation metric for the user according to the metric feature data corresponding to each of at least a part of the multiple fitness actions.   
     
     
         3 . The method according to  claim 2 , wherein extracting, from the motion data by the processor, the metric feature data corresponding to each of the at least a part of the multiple fitness actions performed by the user is independent of an action type of each of the at least a part of the multiple fitness actions. 
     
     
         4 . The method according to  claim 2 , wherein extracting, from the motion data by the processor, the metric feature data corresponding to each of the at least a part of the multiple fitness actions performed by the user comprises:
 performing data reconstruction on the motion data to reduce or eliminate an influence of   an action type of the each of the at least a part of the multiple fitness actions.   
     
     
         5 . The method according to  claim 2 , wherein extracting, from the motion data by the processor, the metric feature data corresponding to each of the at least a part of the multiple fitness actions performed by the user comprises:
 performing singular value decomposition processing on the motion data.   
     
     
         6 . The method according to  claim 1 , wherein determining the value of at least one action evaluation metric of the user according to the motion data comprises:
 obtaining, by the processor, at least one motion data segment from the motion data, each of the at least one motion data segment comprises a segment of the motion data corresponding to a corresponding fitness action performed by the user;   performing, by the processor, data reconstruction on each of the at least one motion data segment to obtain at least one reconstructed data segment; and   determining, by the processor, the value of the at least one action evaluation metric of the user according to the at least one reconstructed data segment.   
     
     
         7 . The method according to  claim 6 , wherein the reconstructed data segment comprises at least one of: virtual principal axis data representative of a signal response to a primary motion of the user, or virtual auxiliary axis data representative of a signal response to sources other than the primary motion of the user. 
     
     
         8 . The method according to  claim 1 , wherein the action quality evaluation result of the user comprises at least one of:
 a statistical result based on the value of the at least one action evaluation metric of the user;   an evaluative description of the at least one action evaluation metric of the user; or   an action improvement suggestion for the user.   
     
     
         9 . A method for evaluating action quality using a wearable device comprising a motion sensor, comprising:
 obtaining, by a processor, motion data from the motion sensor collected during a fitness activity of a user associated with the wearable device, wherein the motion data is associated with a plurality of action types;   extracting, by the processor, at least one motion data segment from the motion data, wherein each of the at least one motion data segment comprises a segment of the motion data corresponding to at least one fitness action;   performing, by the processor, data reconstruction on each of the at least one motion data segment to obtain at least one reconstructed data segment; and   determining, by the processor, an action quality evaluation result of the user according to the at least one reconstructed data segment.   
     
     
         10 . The method according to  claim 9 , wherein:
 the data reconstruction is performed on each of the at least one motion data segment to reduce or eliminate an influence of an action type of the at least one fitness action.   
     
     
         11 . The method according to  claim 9 , wherein the data reconstruction comprises singular value decomposition on each of the at least one motion data segment to obtain the at least one reconstructed data segment. 
     
     
         12 . The method according to  claim 9 , wherein the reconstructed data segment comprises at least one of virtual principal axis data representative of a signal response to a primary motion of the user, or virtual auxiliary axis data representative of a signal response to sources other than the primary motion of the user. 
     
     
         13 . The method according to  claim 12 , wherein determining the action quality evaluation result of the user according to the at least one reconstructed data segment comprises:
 determining a value of a first action evaluation metric of one or more fitness actions performed by the user according to the virtual principal axis data from the reconstructed data segment, and the first action evaluation metric comprises at least one of an action consistency metric, an action stability metric, an action continuity metric, an action variability metric or an action regularity metric.   
     
     
         14 . The method according to  claim 12 , wherein determining the action quality evaluation result of the user according to the at least one reconstructed data segment comprises:
 determining a value of a second action evaluation metric of one or more fitness actions performed by the user according to the virtual auxiliary axis data from the reconstructed data segment, and the second action evaluation metric comprises at least one of an action stability metric or a force control metric.   
     
     
         15 . A non-transitory computer-readable storage medium having a computer program stored thereon, wherein execution of the computer program by a processor cause the processor to implement the method according to  claim 1 . 
     
     
         16 . An electronic device for evaluating action quality of a user, comprising:
 a processor; and   a memory, configured to store instructions executable by the processor;   wherein the processor is configured to execute instructions to perform the method according to  claim 1 .   
     
     
         17 . An electronic device for evaluating action quality of a user, comprising:
 a motion sensor configured to obtain motion data associated with the user when the wearable device is worn by the user; and   a processor configured to execute instructions to perform the method according to  claim 9 .   
     
     
         18 . The method of  claim 9 , wherein:
 the motion data comprises data associated with a plurality of actions with different action types performed by the user, and each of the motion data segment are associated with one or more fitness actions of a same action type.   
     
     
         19 . The method of  claim 9 , wherein extracting at least one motion data segment from the motion data comprises:
 performing action cycle detection on the motion data, and segmenting the motion data into at least one motion data segment based on a result of the action cycle detection, wherein each of the at least one motion data segment is associated with one or more action cycles.   
     
     
         20 . The method of  claim 1 , further comprising:
 determining whether a desired fitness effect is achieved or whether there is a risk of injury based on the value of the at least one action evaluation metric.